Kendi kendini düzenleyen haritalar yöntemiyle Türkçe sesli harflerin sınıflandırılması ve tanınması
Loading...
Date
2012-04-03
Authors
Yürüklü, Emrah
Koçal, Osman H.
Journal Title
Journal ISSN
Volume Title
Publisher
Uludağ Üniversitesi
Abstract
Lokal dinamik modelleme teknikleri kullanılarak zaman serilerini modellemek özellikle son yıllarda oldukça başarılı sonuçlar vermektedir. Kohonen’in 1990 yılında sunduğu ‘Kendi Kendini Düzenleyen Haritalar’ yöntemi ile lokal dinamik modelleme tekniğine farklı bir bakış açısı kazandırılmıştır. Bu yöntem ile, zaman serilerinden türetilen lokal dinamik modeller, sinyalin tüm dinamikleri oldukça başarılı ve kolay bir yöntemle gösterebilmektedir. Zamanla bu teknik pek çok alanda kendine uygulama alanı bulmuş, gerek Kohonen, gerekse diğer uzmanlar tarafından pek çok farklı versiyonu türetilmiştir. Yapılan çalışmada SOM yöntemi kısaca açıklanmış ve bu yöntem yardımıyla Türkçe sesli harfler için sınıflandırma ve tanıma uygulaması yapılmış ve sonuçları tartışılmıştır.
The easiness of putting the model into practice, and making signal or system dynamics and structure observable has made dynamic modeling for time series very popular for the last years. By the years, new versions and approaches of dynamic modeling have been developed and applied to different kind of signals and systems. Kohonen’s suggestion was a new approach to local dynamic modeling which he had offered in 1990. The new technique’s name was ‘Self Organizing Maps’. The innovation of the new approach was its needless of the memory for saving the history of time series. It was because the whole model is updated with the new sample of time series. New versions of this technique are introduced in a lot of different kinds of applications by the years. In this work, ‘Self Organizing Maps’ technique is applied to Turkish vowels and worked on the advantages of the technique.
The easiness of putting the model into practice, and making signal or system dynamics and structure observable has made dynamic modeling for time series very popular for the last years. By the years, new versions and approaches of dynamic modeling have been developed and applied to different kind of signals and systems. Kohonen’s suggestion was a new approach to local dynamic modeling which he had offered in 1990. The new technique’s name was ‘Self Organizing Maps’. The innovation of the new approach was its needless of the memory for saving the history of time series. It was because the whole model is updated with the new sample of time series. New versions of this technique are introduced in a lot of different kinds of applications by the years. In this work, ‘Self Organizing Maps’ technique is applied to Turkish vowels and worked on the advantages of the technique.
Description
Keywords
Kendi kendini düzenleyen haritalar, Lokal dinamik modelleme, Ses tanıma, Self-organising maps, Local dynamic modelling, Speech recognition
Citation
Yürüklü, E. ve Koçal, O. H. (2012). "Kendi kendini düzenleyen haritalar yöntemiyle Türkçe sesli harflerin sınıflandırılması ve tanınması". Uludağ Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 17(1), 1-6.